https://github.com/jmisilo/image-captioning

https://github.com/jmisilo/image-captioning

Last synced: 19 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/jmisilo/image-captioning
• Owner: jmisilo
• Created: 2022-03-23T07:53:25.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2022-04-17T12:18:30.000Z (over 2 years ago)
• Last Synced: 2023-06-15T18:28:58.286Z (over 1 year ago)
• Language: Jupyter Notebook
• Size: 966 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

        
# Image Captioner with CNN + Transformer

Project created for predicting captions for passed images. Train on Flickr30k dataset. Due to issues during training project was stopped, but after some research i resumed it. Goal of the project was to check whether short training model could learn anything about images and create captions for them.

Resources:

- https://www.mdpi.com/2076-3417/8/5/739/pdf - Captioning with stacked Attention Module

- https://github.com/aladdinpersson/Machine-Learning-Collection/tree/master/ML/Pytorch/more_advanced/image_captioning - Image Captioning, Aladdin Persson

- https://github.com/jmisilo/seq2seq-transformer-translation - Decoder architecture code from my previous project